Meta 发布 Muse Spark Open：816B 参数开源权重模型
Meta 出了个 816B 的开源模型 Muse Spark Open，1M 上下文还能多模态，写代码跑智能体任务，感兴趣可以自己下下来测测。
Meta 发布开源权重模型 Muse Spark Open，总参数量 816B，激活参数 42B。上下文窗口达 1M token，支持文本、图像、视频、音频的原生多模态输入。模型定位是编程与智能体任务，官方称其在长时程任务、复杂软件工程和多步推理上表现突出，并称其为目前美国最强的开源权重模型。具体成绩需自行测试验证，文中未附基准数字。
Damn! Looking at the results, Meta really cooked here! More progress on frontier open models is always a big deal. Great to see Meta going back to its roots. The only way to know this checkpoint's quality is to test it yourself. AI at Meta @AIatMeta Today we’re releasing Muse Spark Open, the most capable US open-weight model to date. Built for coding and agentic work, it excels at long-horizon tasks, complex software engineering, and multi-step reasoning. Key Model Specs: → 816B total / 42B active parameters → 1M token context window → Natively multimodal across text, image, video, audio 🔗 View Quoted Tweet 💬 2 🔄 1 ❤️ 11 👀 1650 📊 3 ⚡
